Related papers: Critical assessment of machine-learned repulsive p…

Machine Learning (ML) approximations to Density Functional Theory (DFT) potential energy surfaces (PESs) are showing great promise for reducing the computational cost of accurate molecular simulations, but at present they are not applicable…

Tight-binding (TB) molecular dynamics (MD) has emerged as a powerful method for investigating the atomic-scale structure of materials --- in particular the interplay between structural and electronic properties --- bridging the gap between…

Deep learning electronic structures from ab initio calculations holds great potential to revolutionize computational materials studies. While existing methods proved success in deep-learning density functional theory (DFT) Hamiltonian…

Quantum chemistry provides chemists with invaluable information, but the high computational cost limits the size and type of systems that can be studied. Machine learning (ML) has emerged as a means to dramatically lower cost while…

Moment Tensor Potentials (MTPs) are machine-learning interatomic potentials whose basis functions are typically selected using a level-based scheme that is data-agnostic. We introduce a post-training, cost-aware pruning strategy that…

Si and its oxides have been extensively explored in theoretical research due to their technological and industrial importance. Simultaneously describing interatomic interactions within both Si and SiO$_2$ without the use of \textit{ab…

A generalization of the density-functional based tight-binding method (DFTB) for the use with range-separated exchange-correlation functionals is presented. It is based on the Generalized Kohn-Sham (GKS) formalism and employs the density…

This paper evaluates the use of metamorphic relations to enhance the robustness and real-world performance of machine learning models. We propose a Metamorphic Retraining Framework, which applies metamorphic relations to data and utilizes…

Tin (Sn) plays a crucial role in studying the dynamic mechanical responses of ductile metals under shock loading. Atomistic simulations serves to unveil the nano-scale mechanisms for critical behaviors of dynamic responses. However,…

Understanding the mechanical properties of solid-state materials at the atomic scale is crucial for developing novel materials. For example, amorphous LiSi alloys are attractive anode materials for solid-state Li-ion batteries but face…

The marriage of density functional theory (DFT) and deep learning methods has the potential to revolutionize modern computational materials science. Here we develop a deep neural network approach to represent DFT Hamiltonian (DeepH) of…

Density functional theory is the standard theory for computing the electronic structure of materials, which is based on a functional that maps the electron density to the energy. However, a rigorous form of the functional is not known and…

A new method for calculating the total energy of Si systems is presented. The method is based on the effective-medium theory concept of a reference system. Instead of calculating the energy of an atom in the system of interest a reference…

Machine Learning Potentials (MLPs) can enable simulations of ab initio accuracy at orders of magnitude lower computational cost. However, their effectiveness hinges on the availability of considerable datasets to ensure robust…

Machine-learning interatomic potentials are widely used as computationally efficient surrogates for density functional theory in atomistic simulations, enabling large-scale, long-time modeling of materials systems. We investigate how…

In this work we propose a chemically-informed data-driven approach to benchmark the approximate density-functional tight-binding (DFTB) excited state (ES) methods that are currently available within the DFTB+ suite. By taking advantage of…

An empirical $s_cp^3_a$ tight-binding (TB) model is applied to the investigation of electronic states in semiconductor quantum dots. A basis set of three $p$-orbitals at the anions and one $s$-orbital at the cations is chosen. Matrix…

As one of the most widely used metal tube bending methods, the rotary draw bending (RDB) process enables reliable and high-precision metal tube bending forming (MTBF). The forming accuracy is seriously affected by the springback and other…

Machine-learned interatomic potentials are revolutionising atomistic materials simulations by providing accurate and scalable predictions within the scope covered by the training data. However, generation of an accurate and robust training…

Machine-learned interatomic potentials (MLIPs) have become the gold standard for atomistic simulations, yet their extension to magnetic materials remains challenging because spin fluctuations must be captured either explicitly or…